summaryrefslogtreecommitdiff
path: root/kernel/rcu/tree.h
blob: bae7925c497feecc5116b46b23ac8194e77a66d4 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
/* SPDX-License-Identifier: GPL-2.0+ */
/*
 * Read-Copy Update mechanism for mutual exclusion (tree-based version)
 * Internal non-public definitions.
 *
 * Copyright IBM Corporation, 2008
 *
 * Author: Ingo Molnar <mingo@elte.hu>
 *	   Paul E. McKenney <paulmck@linux.ibm.com>
 */

#include <linux/cache.h>
#include <linux/kthread.h>
#include <linux/spinlock.h>
#include <linux/rtmutex.h>
#include <linux/threads.h>
#include <linux/cpumask.h>
#include <linux/seqlock.h>
#include <linux/swait.h>
#include <linux/rcu_node_tree.h>

#include "rcu_segcblist.h"

/* Communicate arguments to a kthread worker handler. */
struct rcu_exp_work {
	unsigned long rew_s;
	struct kthread_work rew_work;
};

/* RCU's kthread states for tracing. */
#define RCU_KTHREAD_STOPPED  0
#define RCU_KTHREAD_RUNNING  1
#define RCU_KTHREAD_WAITING  2
#define RCU_KTHREAD_OFFCPU   3
#define RCU_KTHREAD_YIELDING 4
#define RCU_KTHREAD_MAX      4

/*
 * Definition for node within the RCU grace-period-detection hierarchy.
 */
struct rcu_node {
	raw_spinlock_t __private lock;	/* Root rcu_node's lock protects */
					/*  some rcu_state fields as well as */
					/*  following. */
	unsigned long gp_seq;	/* Track rsp->gp_seq. */
	unsigned long gp_seq_needed; /* Track furthest future GP request. */
	unsigned long completedqs; /* All QSes done for this node. */
	unsigned long qsmask;	/* CPUs or groups that need to switch in */
				/*  order for current grace period to proceed.*/
				/*  In leaf rcu_node, each bit corresponds to */
				/*  an rcu_data structure, otherwise, each */
				/*  bit corresponds to a child rcu_node */
				/*  structure. */
	unsigned long rcu_gp_init_mask;	/* Mask of offline CPUs at GP init. */
	unsigned long qsmaskinit;
				/* Per-GP initial value for qsmask. */
				/*  Initialized from ->qsmaskinitnext at the */
				/*  beginning of each grace period. */
	unsigned long qsmaskinitnext;
	unsigned long expmask;	/* CPUs or groups that need to check in */
				/*  to allow the current expedited GP */
				/*  to complete. */
	unsigned long expmaskinit;
				/* Per-GP initial values for expmask. */
				/*  Initialized from ->expmaskinitnext at the */
				/*  beginning of each expedited GP. */
	unsigned long expmaskinitnext;
				/* Online CPUs for next expedited GP. */
				/*  Any CPU that has ever been online will */
				/*  have its bit set. */
	struct kthread_worker *exp_kworker;
				/* Workers performing per node expedited GP */
				/* initialization. */
	unsigned long cbovldmask;
				/* CPUs experiencing callback overload. */
	unsigned long ffmask;	/* Fully functional CPUs. */
	unsigned long grpmask;	/* Mask to apply to parent qsmask. */
				/*  Only one bit will be set in this mask. */
	int	grplo;		/* lowest-numbered CPU here. */
	int	grphi;		/* highest-numbered CPU here. */
	u8	grpnum;		/* group number for next level up. */
	u8	level;		/* root is at level 0. */
	bool	wait_blkd_tasks;/* Necessary to wait for blocked tasks to */
				/*  exit RCU read-side critical sections */
				/*  before propagating offline up the */
				/*  rcu_node tree? */
	struct rcu_node *parent;
	struct list_head blkd_tasks;
				/* Tasks blocked in RCU read-side critical */
				/*  section.  Tasks are placed at the head */
				/*  of this list and age towards the tail. */
	struct list_head *gp_tasks;
				/* Pointer to the first task blocking the */
				/*  current grace period, or NULL if there */
				/*  is no such task. */
	struct list_head *exp_tasks;
				/* Pointer to the first task blocking the */
				/*  current expedited grace period, or NULL */
				/*  if there is no such task.  If there */
				/*  is no current expedited grace period, */
				/*  then there can cannot be any such task. */
	struct list_head *boost_tasks;
				/* Pointer to first task that needs to be */
				/*  priority boosted, or NULL if no priority */
				/*  boosting is needed for this rcu_node */
				/*  structure.  If there are no tasks */
				/*  queued on this rcu_node structure that */
				/*  are blocking the current grace period, */
				/*  there can be no such task. */
	struct rt_mutex boost_mtx;
				/* Used only for the priority-boosting */
				/*  side effect, not as a lock. */
	unsigned long boost_time;
				/* When to start boosting (jiffies). */
	struct mutex kthread_mutex;
				/* Exclusion for thread spawning and affinity */
				/*  manipulation. */
	struct task_struct *boost_kthread_task;
				/* kthread that takes care of priority */
				/*  boosting for this rcu_node structure. */
	unsigned int boost_kthread_status;
				/* State of boost_kthread_task for tracing. */
	unsigned long n_boosts;	/* Number of boosts for this rcu_node structure. */
#ifdef CONFIG_RCU_NOCB_CPU
	struct swait_queue_head nocb_gp_wq[2];
				/* Place for rcu_nocb_kthread() to wait GP. */
#endif /* #ifdef CONFIG_RCU_NOCB_CPU */
	raw_spinlock_t fqslock ____cacheline_internodealigned_in_smp;

	spinlock_t exp_lock ____cacheline_internodealigned_in_smp;
	unsigned long exp_seq_rq;
	wait_queue_head_t exp_wq[4];
	struct rcu_exp_work rew;
	bool exp_need_flush;	/* Need to flush workitem? */
	raw_spinlock_t exp_poll_lock;
				/* Lock and data for polled expedited grace periods. */
	unsigned long exp_seq_poll_rq;
	struct work_struct exp_poll_wq;
} ____cacheline_internodealigned_in_smp;

/*
 * Bitmasks in an rcu_node cover the interval [grplo, grphi] of CPU IDs, and
 * are indexed relative to this interval rather than the global CPU ID space.
 * This generates the bit for a CPU in node-local masks.
 */
#define leaf_node_cpu_bit(rnp, cpu) (BIT((cpu) - (rnp)->grplo))

/*
 * Union to allow "aggregate OR" operation on the need for a quiescent
 * state by the normal and expedited grace periods.
 */
union rcu_noqs {
	struct {
		u8 norm;
		u8 exp;
	} b; /* Bits. */
	u16 s; /* Set of bits, aggregate OR here. */
};

/*
 * Record the snapshot of the core stats at half of the first RCU stall timeout.
 * The member gp_seq is used to ensure that all members are updated only once
 * during the sampling period. The snapshot is taken only if this gp_seq is not
 * equal to rdp->gp_seq.
 */
struct rcu_snap_record {
	unsigned long	gp_seq;		/* Track rdp->gp_seq counter */
	u64		cputime_irq;	/* Accumulated cputime of hard irqs */
	u64		cputime_softirq;/* Accumulated cputime of soft irqs */
	u64		cputime_system; /* Accumulated cputime of kernel tasks */
	unsigned long	nr_hardirqs;	/* Accumulated number of hard irqs */
	unsigned int	nr_softirqs;	/* Accumulated number of soft irqs */
	unsigned long long nr_csw;	/* Accumulated number of task switches */
	unsigned long   jiffies;	/* Track jiffies value */
};

/* Per-CPU data for read-copy update. */
struct rcu_data {
	/* 1) quiescent-state and grace-period handling : */
	unsigned long	gp_seq;		/* Track rsp->gp_seq counter. */
	unsigned long	gp_seq_needed;	/* Track furthest future GP request. */
	union rcu_noqs	cpu_no_qs;	/* No QSes yet for this CPU. */
	bool		core_needs_qs;	/* Core waits for quiescent state. */
	bool		beenonline;	/* CPU online at least once. */
	bool		gpwrap;		/* Possible ->gp_seq wrap. */
	bool		cpu_started;	/* RCU watching this onlining CPU. */
	struct rcu_node *mynode;	/* This CPU's leaf of hierarchy */
	unsigned long grpmask;		/* Mask to apply to leaf qsmask. */
	unsigned long	ticks_this_gp;	/* The number of scheduling-clock */
					/*  ticks this CPU has handled */
					/*  during and after the last grace */
					/* period it is aware of. */
	struct irq_work defer_qs_iw;	/* Obtain later scheduler attention. */
	bool defer_qs_iw_pending;	/* Scheduler attention pending? */
	struct work_struct strict_work;	/* Schedule readers for strict GPs. */

	/* 2) batch handling */
	struct rcu_segcblist cblist;	/* Segmented callback list, with */
					/* different callbacks waiting for */
					/* different grace periods. */
	long		qlen_last_fqs_check;
					/* qlen at last check for QS forcing */
	unsigned long	n_cbs_invoked;	/* # callbacks invoked since boot. */
	unsigned long	n_force_qs_snap;
					/* did other CPU force QS recently? */
	long		blimit;		/* Upper limit on a processed batch */

	/* 3) dynticks interface. */
	int dynticks_snap;		/* Per-GP tracking for dynticks. */
	bool rcu_need_heavy_qs;		/* GP old, so heavy quiescent state! */
	bool rcu_urgent_qs;		/* GP old need light quiescent state. */
	bool rcu_forced_tick;		/* Forced tick to provide QS. */
	bool rcu_forced_tick_exp;	/*   ... provide QS to expedited GP. */

	/* 4) rcu_barrier(), OOM callbacks, and expediting. */
	unsigned long barrier_seq_snap;	/* Snap of rcu_state.barrier_sequence. */
	struct rcu_head barrier_head;
	int exp_dynticks_snap;		/* Double-check need for IPI. */

	/* 5) Callback offloading. */
#ifdef CONFIG_RCU_NOCB_CPU
	struct swait_queue_head nocb_cb_wq; /* For nocb kthreads to sleep on. */
	struct swait_queue_head nocb_state_wq; /* For offloading state changes */
	struct task_struct *nocb_gp_kthread;
	raw_spinlock_t nocb_lock;	/* Guard following pair of fields. */
	atomic_t nocb_lock_contended;	/* Contention experienced. */
	int nocb_defer_wakeup;		/* Defer wakeup of nocb_kthread. */
	struct timer_list nocb_timer;	/* Enforce finite deferral. */
	unsigned long nocb_gp_adv_time;	/* Last call_rcu() CB adv (jiffies). */
	struct mutex nocb_gp_kthread_mutex; /* Exclusion for nocb gp kthread */
					    /* spawning */

	/* The following fields are used by call_rcu, hence own cacheline. */
	raw_spinlock_t nocb_bypass_lock ____cacheline_internodealigned_in_smp;
	struct rcu_cblist nocb_bypass;	/* Lock-contention-bypass CB list. */
	unsigned long nocb_bypass_first; /* Time (jiffies) of first enqueue. */
	unsigned long nocb_nobypass_last; /* Last ->cblist enqueue (jiffies). */
	int nocb_nobypass_count;	/* # ->cblist enqueues at ^^^ time. */

	/* The following fields are used by GP kthread, hence own cacheline. */
	raw_spinlock_t nocb_gp_lock ____cacheline_internodealigned_in_smp;
	u8 nocb_gp_sleep;		/* Is the nocb GP thread asleep? */
	u8 nocb_gp_bypass;		/* Found a bypass on last scan? */
	u8 nocb_gp_gp;			/* GP to wait for on last scan? */
	unsigned long nocb_gp_seq;	/*  If so, ->gp_seq to wait for. */
	unsigned long nocb_gp_loops;	/* # passes through wait code. */
	struct swait_queue_head nocb_gp_wq; /* For nocb kthreads to sleep on. */
	bool nocb_cb_sleep;		/* Is the nocb CB thread asleep? */
	struct task_struct *nocb_cb_kthread;
	struct list_head nocb_head_rdp; /*
					 * Head of rcu_data list in wakeup chain,
					 * if rdp_gp.
					 */
	struct list_head nocb_entry_rdp; /* rcu_data node in wakeup chain. */
	struct rcu_data *nocb_toggling_rdp; /* rdp queued for (de-)offloading */

	/* The following fields are used by CB kthread, hence new cacheline. */
	struct rcu_data *nocb_gp_rdp ____cacheline_internodealigned_in_smp;
					/* GP rdp takes GP-end wakeups. */
#endif /* #ifdef CONFIG_RCU_NOCB_CPU */

	/* 6) RCU priority boosting. */
	struct task_struct *rcu_cpu_kthread_task;
					/* rcuc per-CPU kthread or NULL. */
	unsigned int rcu_cpu_kthread_status;
	char rcu_cpu_has_work;
	unsigned long rcuc_activity;

	/* 7) Diagnostic data, including RCU CPU stall warnings. */
	unsigned int softirq_snap;	/* Snapshot of softirq activity. */
	/* ->rcu_iw* fields protected by leaf rcu_node ->lock. */
	struct irq_work rcu_iw;		/* Check for non-irq activity. */
	bool rcu_iw_pending;		/* Is ->rcu_iw pending? */
	unsigned long rcu_iw_gp_seq;	/* ->gp_seq associated with ->rcu_iw. */
	unsigned long rcu_ofl_gp_seq;	/* ->gp_seq at last offline. */
	short rcu_ofl_gp_state;		/* ->gp_state at last offline. */
	unsigned long rcu_onl_gp_seq;	/* ->gp_seq at last online. */
	short rcu_onl_gp_state;		/* ->gp_state at last online. */
	unsigned long last_fqs_resched;	/* Time of last rcu_resched(). */
	unsigned long last_sched_clock;	/* Jiffies of last rcu_sched_clock_irq(). */
	struct rcu_snap_record snap_record; /* Snapshot of core stats at half of */
					    /* the first RCU stall timeout */

	long lazy_len;			/* Length of buffered lazy callbacks. */
	int cpu;
};

/* Values for nocb_defer_wakeup field in struct rcu_data. */
#define RCU_NOCB_WAKE_NOT	0
#define RCU_NOCB_WAKE_BYPASS	1
#define RCU_NOCB_WAKE_LAZY	2
#define RCU_NOCB_WAKE		3
#define RCU_NOCB_WAKE_FORCE	4

#define RCU_JIFFIES_TILL_FORCE_QS (1 + (HZ > 250) + (HZ > 500))
					/* For jiffies_till_first_fqs and */
					/*  and jiffies_till_next_fqs. */

#define RCU_JIFFIES_FQS_DIV	256	/* Very large systems need more */
					/*  delay between bouts of */
					/*  quiescent-state forcing. */

#define RCU_STALL_RAT_DELAY	2	/* Allow other CPUs time to take */
					/*  at least one scheduling clock */
					/*  irq before ratting on them. */

#define rcu_wait(cond)							\
do {									\
	for (;;) {							\
		set_current_state(TASK_INTERRUPTIBLE);			\
		if (cond)						\
			break;						\
		schedule();						\
	}								\
	__set_current_state(TASK_RUNNING);				\
} while (0)

/*
 * A max threshold for synchronize_rcu() users which are
 * awaken directly by the rcu_gp_kthread(). Left part is
 * deferred to the main worker.
 */
#define SR_MAX_USERS_WAKE_FROM_GP 5
#define SR_NORMAL_GP_WAIT_HEAD_MAX 5

struct sr_wait_node {
	atomic_t inuse;
	struct llist_node node;
};

/*
 * RCU global state, including node hierarchy.  This hierarchy is
 * represented in "heap" form in a dense array.  The root (first level)
 * of the hierarchy is in ->node[0] (referenced by ->level[0]), the second
 * level in ->node[1] through ->node[m] (->node[1] referenced by ->level[1]),
 * and the third level in ->node[m+1] and following (->node[m+1] referenced
 * by ->level[2]).  The number of levels is determined by the number of
 * CPUs and by CONFIG_RCU_FANOUT.  Small systems will have a "hierarchy"
 * consisting of a single rcu_node.
 */
struct rcu_state {
	struct rcu_node node[NUM_RCU_NODES];	/* Hierarchy. */
	struct rcu_node *level[RCU_NUM_LVLS + 1];
						/* Hierarchy levels (+1 to */
						/*  shut bogus gcc warning) */
	int ncpus;				/* # CPUs seen so far. */
	int n_online_cpus;			/* # CPUs online for RCU. */

	/* The following fields are guarded by the root rcu_node's lock. */

	unsigned long gp_seq ____cacheline_internodealigned_in_smp;
						/* Grace-period sequence #. */
	unsigned long gp_max;			/* Maximum GP duration in */
						/*  jiffies. */
	struct task_struct *gp_kthread;		/* Task for grace periods. */
	struct swait_queue_head gp_wq;		/* Where GP task waits. */
	short gp_flags;				/* Commands for GP task. */
	short gp_state;				/* GP kthread sleep state. */
	unsigned long gp_wake_time;		/* Last GP kthread wake. */
	unsigned long gp_wake_seq;		/* ->gp_seq at ^^^. */
	unsigned long gp_seq_polled;		/* GP seq for polled API. */
	unsigned long gp_seq_polled_snap;	/* ->gp_seq_polled at normal GP start. */
	unsigned long gp_seq_polled_exp_snap;	/* ->gp_seq_polled at expedited GP start. */

	/* End of fields guarded by root rcu_node's lock. */

	struct mutex barrier_mutex;		/* Guards barrier fields. */
	atomic_t barrier_cpu_count;		/* # CPUs waiting on. */
	struct completion barrier_completion;	/* Wake at barrier end. */
	unsigned long barrier_sequence;		/* ++ at start and end of */
						/*  rcu_barrier(). */
	/* End of fields guarded by barrier_mutex. */

	raw_spinlock_t barrier_lock;		/* Protects ->barrier_seq_snap. */

	struct mutex exp_mutex;			/* Serialize expedited GP. */
	struct mutex exp_wake_mutex;		/* Serialize wakeup. */
	unsigned long expedited_sequence;	/* Take a ticket. */
	atomic_t expedited_need_qs;		/* # CPUs left to check in. */
	struct swait_queue_head expedited_wq;	/* Wait for check-ins. */
	int ncpus_snap;				/* # CPUs seen last time. */
	u8 cbovld;				/* Callback overload now? */
	u8 cbovldnext;				/* ^        ^  next time? */

	unsigned long jiffies_force_qs;		/* Time at which to invoke */
						/*  force_quiescent_state(). */
	unsigned long jiffies_kick_kthreads;	/* Time at which to kick */
						/*  kthreads, if configured. */
	unsigned long n_force_qs;		/* Number of calls to */
						/*  force_quiescent_state(). */
	unsigned long gp_start;			/* Time at which GP started, */
						/*  but in jiffies. */
	unsigned long gp_end;			/* Time last GP ended, again */
						/*  in jiffies. */
	unsigned long gp_activity;		/* Time of last GP kthread */
						/*  activity in jiffies. */
	unsigned long gp_req_activity;		/* Time of last GP request */
						/*  in jiffies. */
	unsigned long jiffies_stall;		/* Time at which to check */
						/*  for CPU stalls. */
	int nr_fqs_jiffies_stall;		/* Number of fqs loops after
						 * which read jiffies and set
						 * jiffies_stall. Stall
						 * warnings disabled if !0. */
	unsigned long jiffies_resched;		/* Time at which to resched */
						/*  a reluctant CPU. */
	unsigned long n_force_qs_gpstart;	/* Snapshot of n_force_qs at */
						/*  GP start. */
	const char *name;			/* Name of structure. */
	char abbr;				/* Abbreviated name. */

	arch_spinlock_t ofl_lock ____cacheline_internodealigned_in_smp;
						/* Synchronize offline with */
						/*  GP pre-initialization. */
	int nocb_is_setup;			/* nocb is setup from boot */

	/* synchronize_rcu() part. */
	struct llist_head srs_next;	/* request a GP users. */
	struct llist_node *srs_wait_tail; /* wait for GP users. */
	struct llist_node *srs_done_tail; /* ready for GP users. */
	struct sr_wait_node srs_wait_nodes[SR_NORMAL_GP_WAIT_HEAD_MAX];
	struct work_struct srs_cleanup_work;
};

/* Values for rcu_state structure's gp_flags field. */
#define RCU_GP_FLAG_INIT 0x1	/* Need grace-period initialization. */
#define RCU_GP_FLAG_FQS  0x2	/* Need grace-period quiescent-state forcing. */
#define RCU_GP_FLAG_OVLD 0x4	/* Experiencing callback overload. */

/* Values for rcu_state structure's gp_state field. */
#define RCU_GP_IDLE	 0	/* Initial state and no GP in progress. */
#define RCU_GP_WAIT_GPS  1	/* Wait for grace-period start. */
#define RCU_GP_DONE_GPS  2	/* Wait done for grace-period start. */
#define RCU_GP_ONOFF     3	/* Grace-period initialization hotplug. */
#define RCU_GP_INIT      4	/* Grace-period initialization. */
#define RCU_GP_WAIT_FQS  5	/* Wait for force-quiescent-state time. */
#define RCU_GP_DOING_FQS 6	/* Wait done for force-quiescent-state time. */
#define RCU_GP_CLEANUP   7	/* Grace-period cleanup started. */
#define RCU_GP_CLEANED   8	/* Grace-period cleanup complete. */

/*
 * In order to export the rcu_state name to the tracing tools, it
 * needs to be added in the __tracepoint_string section.
 * This requires defining a separate variable tp_<sname>_varname
 * that points to the string being used, and this will allow
 * the tracing userspace tools to be able to decipher the string
 * address to the matching string.
 */
#ifdef CONFIG_PREEMPT_RCU
#define RCU_ABBR 'p'
#define RCU_NAME_RAW "rcu_preempt"
#else /* #ifdef CONFIG_PREEMPT_RCU */
#define RCU_ABBR 's'
#define RCU_NAME_RAW "rcu_sched"
#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
#ifndef CONFIG_TRACING
#define RCU_NAME RCU_NAME_RAW
#else /* #ifdef CONFIG_TRACING */
static char rcu_name[] = RCU_NAME_RAW;
static const char *tp_rcu_varname __used __tracepoint_string = rcu_name;
#define RCU_NAME rcu_name
#endif /* #else #ifdef CONFIG_TRACING */

/* Forward declarations for tree_plugin.h */
static void rcu_bootup_announce(void);
static void rcu_qs(void);
static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp);
#ifdef CONFIG_HOTPLUG_CPU
static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
#endif /* #ifdef CONFIG_HOTPLUG_CPU */
static int rcu_print_task_exp_stall(struct rcu_node *rnp);
static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp);
static void rcu_flavor_sched_clock_irq(int user);
static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck);
static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
static void rcu_preempt_boost_start_gp(struct rcu_node *rnp);
static bool rcu_is_callbacks_kthread(struct rcu_data *rdp);
static void rcu_cpu_kthread_setup(unsigned int cpu);
static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp);
static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
static bool rcu_preempt_need_deferred_qs(struct task_struct *t);
static void zero_cpu_stall_ticks(struct rcu_data *rdp);
static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp);
static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq);
static void rcu_init_one_nocb(struct rcu_node *rnp);
static bool wake_nocb_gp(struct rcu_data *rdp, bool force);
static bool rcu_nocb_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
				  unsigned long j, bool lazy);
static void call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *head,
			  rcu_callback_t func, unsigned long flags, bool lazy);
static void __maybe_unused __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_empty,
						unsigned long flags);
static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp, int level);
static bool do_nocb_deferred_wakeup(struct rcu_data *rdp);
static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp);
static void rcu_spawn_cpu_nocb_kthread(int cpu);
static void show_rcu_nocb_state(struct rcu_data *rdp);
static void rcu_nocb_lock(struct rcu_data *rdp);
static void rcu_nocb_unlock(struct rcu_data *rdp);
static void rcu_nocb_unlock_irqrestore(struct rcu_data *rdp,
				       unsigned long flags);
static void rcu_lockdep_assert_cblist_protected(struct rcu_data *rdp);
#ifdef CONFIG_RCU_NOCB_CPU
static void __init rcu_organize_nocb_kthreads(void);

/*
 * Disable IRQs before checking offloaded state so that local
 * locking is safe against concurrent de-offloading.
 */
#define rcu_nocb_lock_irqsave(rdp, flags)			\
do {								\
	local_irq_save(flags);					\
	if (rcu_segcblist_is_offloaded(&(rdp)->cblist))	\
		raw_spin_lock(&(rdp)->nocb_lock);		\
} while (0)
#else /* #ifdef CONFIG_RCU_NOCB_CPU */
#define rcu_nocb_lock_irqsave(rdp, flags) local_irq_save(flags)
#endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */

static void rcu_bind_gp_kthread(void);
static bool rcu_nohz_full_cpu(void);

/* Forward declarations for tree_stall.h */
static void record_gp_stall_check_time(void);
static void rcu_iw_handler(struct irq_work *iwp);
static void check_cpu_stall(struct rcu_data *rdp);
static void rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp,
				     const unsigned long gpssdelay);

/* Forward declarations for tree_exp.h. */
static void sync_rcu_do_polled_gp(struct work_struct *wp);